Matches in SemOpenAlex for { <https://semopenalex.org/work/W2460163328> ?p ?o ?g. }
- W2460163328 abstract "Deep Reinforcement Learning (DRL) is a trending field of research, showing great promise in many challenging problems such as playing Atari, solving Go and controlling robots. While DRL agents perform well in practice we are still missing the tools to analayze their performance and visualize the temporal abstractions that they learn. In this paper, we present a novel method that automatically discovers an internal Semi Markov Decision Process (SMDP) model in the Deep Q Network's (DQN) learned representation. We suggest a novel visualization method that represents the SMDP model by a directed graph and visualize it above a t-SNE map. We show how can we interpret the agent's policy and give evidence for the hierarchical state aggregation that DQNs are learning automatically. Our algorithm is fully automatic, does not require any domain specific knowledge and is evaluated by a novel likelihood based evaluation criteria." @default.
- W2460163328 created "2016-07-22" @default.
- W2460163328 creator A5018613019 @default.
- W2460163328 creator A5036260775 @default.
- W2460163328 creator A5045966421 @default.
- W2460163328 date "2016-06-22" @default.
- W2460163328 modified "2023-09-27" @default.
- W2460163328 title "Visualizing Dynamics: from t-SNE to SEMI-MDPs." @default.
- W2460163328 cites W141456974 @default.
- W2460163328 cites W1557798492 @default.
- W2460163328 cites W1595483645 @default.
- W2460163328 cites W1631187438 @default.
- W2460163328 cites W1849277567 @default.
- W2460163328 cites W1875842236 @default.
- W2460163328 cites W1968653071 @default.
- W2460163328 cites W2001141328 @default.
- W2460163328 cites W2016381774 @default.
- W2460163328 cites W2057895073 @default.
- W2460163328 cites W2063385051 @default.
- W2460163328 cites W2109910161 @default.
- W2460163328 cites W2127218421 @default.
- W2460163328 cites W2132022337 @default.
- W2460163328 cites W2133254839 @default.
- W2460163328 cites W2145339207 @default.
- W2460163328 cites W2187089797 @default.
- W2460163328 cites W2335959470 @default.
- W2460163328 cites W2344023930 @default.
- W2460163328 cites W2949667497 @default.
- W2460163328 cites W2950708852 @default.
- W2460163328 cites W3122153094 @default.
- W2460163328 hasPublicationYear "2016" @default.
- W2460163328 type Work @default.
- W2460163328 sameAs 2460163328 @default.
- W2460163328 citedByCount "4" @default.
- W2460163328 countsByYear W24601633282017 @default.
- W2460163328 countsByYear W24601633282018 @default.
- W2460163328 countsByYear W24601633282019 @default.
- W2460163328 crossrefType "posted-content" @default.
- W2460163328 hasAuthorship W2460163328A5018613019 @default.
- W2460163328 hasAuthorship W2460163328A5036260775 @default.
- W2460163328 hasAuthorship W2460163328A5045966421 @default.
- W2460163328 hasConcept C105795698 @default.
- W2460163328 hasConcept C106189395 @default.
- W2460163328 hasConcept C119857082 @default.
- W2460163328 hasConcept C132525143 @default.
- W2460163328 hasConcept C134306372 @default.
- W2460163328 hasConcept C154945302 @default.
- W2460163328 hasConcept C159886148 @default.
- W2460163328 hasConcept C17744445 @default.
- W2460163328 hasConcept C199360897 @default.
- W2460163328 hasConcept C199539241 @default.
- W2460163328 hasConcept C202444582 @default.
- W2460163328 hasConcept C2776359362 @default.
- W2460163328 hasConcept C33923547 @default.
- W2460163328 hasConcept C36464697 @default.
- W2460163328 hasConcept C36503486 @default.
- W2460163328 hasConcept C41008148 @default.
- W2460163328 hasConcept C80444323 @default.
- W2460163328 hasConcept C94625758 @default.
- W2460163328 hasConcept C9652623 @default.
- W2460163328 hasConcept C97541855 @default.
- W2460163328 hasConcept C98045186 @default.
- W2460163328 hasConceptScore W2460163328C105795698 @default.
- W2460163328 hasConceptScore W2460163328C106189395 @default.
- W2460163328 hasConceptScore W2460163328C119857082 @default.
- W2460163328 hasConceptScore W2460163328C132525143 @default.
- W2460163328 hasConceptScore W2460163328C134306372 @default.
- W2460163328 hasConceptScore W2460163328C154945302 @default.
- W2460163328 hasConceptScore W2460163328C159886148 @default.
- W2460163328 hasConceptScore W2460163328C17744445 @default.
- W2460163328 hasConceptScore W2460163328C199360897 @default.
- W2460163328 hasConceptScore W2460163328C199539241 @default.
- W2460163328 hasConceptScore W2460163328C202444582 @default.
- W2460163328 hasConceptScore W2460163328C2776359362 @default.
- W2460163328 hasConceptScore W2460163328C33923547 @default.
- W2460163328 hasConceptScore W2460163328C36464697 @default.
- W2460163328 hasConceptScore W2460163328C36503486 @default.
- W2460163328 hasConceptScore W2460163328C41008148 @default.
- W2460163328 hasConceptScore W2460163328C80444323 @default.
- W2460163328 hasConceptScore W2460163328C94625758 @default.
- W2460163328 hasConceptScore W2460163328C9652623 @default.
- W2460163328 hasConceptScore W2460163328C97541855 @default.
- W2460163328 hasConceptScore W2460163328C98045186 @default.
- W2460163328 hasLocation W24601633281 @default.
- W2460163328 hasOpenAccess W2460163328 @default.
- W2460163328 hasPrimaryLocation W24601633281 @default.
- W2460163328 hasRelatedWork W1838394841 @default.
- W2460163328 hasRelatedWork W2402540331 @default.
- W2460163328 hasRelatedWork W2428397683 @default.
- W2460163328 hasRelatedWork W2523124567 @default.
- W2460163328 hasRelatedWork W2558634851 @default.
- W2460163328 hasRelatedWork W2749952662 @default.
- W2460163328 hasRelatedWork W2751395938 @default.
- W2460163328 hasRelatedWork W2786019934 @default.
- W2460163328 hasRelatedWork W2808213164 @default.
- W2460163328 hasRelatedWork W2907361867 @default.
- W2460163328 hasRelatedWork W2950708852 @default.
- W2460163328 hasRelatedWork W2953243993 @default.
- W2460163328 hasRelatedWork W2954142106 @default.
- W2460163328 hasRelatedWork W2956149426 @default.